Rainfall prediction using Extreme Gradient Boosting
Muchamad Taufiq Anwar, Edy Winarno, Wiwien Hadikurniawati, Mega Novita
Abstract
Abstract Rainfall greatly affects human life in various sectors including agriculture, transportation, etc. and also can affect natural disasters such as drought, floods, and landslides. This situation prompts us to build an accurate rainfall prediction model so that prescriptive measures can be made. Previous research on rainfall prediction uses models that have their limitations and thus produce poor performance. This study aims to build a multivariate rainfall prediction model using the best performing technique to date namely the Extreme Gradient Boosting. This model is built based on 7 years of historical weather data collected by the weather station. The result had demonstrated that the model is capable of producing accurate predictions for daily rainfall estimates with training RMSE of 2.7 mm and the testing MAE of 8.8 mm.